Zero-Shot Kernel Learning

Hongguang Zhang, Piotr Koniusz; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7670-7679

Abstract


In this paper, we address an open problem of zero-shot learning. Its principle is based on learning a mapping that associates feature vectors extracted from i.e. images and attribute vectors that describe objects and/or scenes of interest. In turns, this allows classifying unseen object classes and/or scenes by matching feature vectors via mapping to a newly defined attribute vector describing a new class. Due to importance of such a learning task, there exist many methods that learn semantic, probabilistic, linear or piece-wise linear mappings. In contrast, we apply well-established kernel methods to learn a non-linear mapping between the feature and attribute spaces. We propose an easy learning objective with orthogonality constraints inspired by the Linear Discriminant Analysis, Kernel-Target Alignment and Kernel Polarization methods. We evaluate the performance of our algorithm on the Polynomial as well as shift-invariant Gaussian and Cauchy kernels. Despite simplicity of our approach, we obtain state-of-the-art results on several zero-shot learning datasets and benchmarks including very recent AWA2 dataset.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2018_CVPR,
author = {Zhang, Hongguang and Koniusz, Piotr},
title = {Zero-Shot Kernel Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}